Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7255
    Prev
    Next
    INDEX
    Explanations

    mentions of familial or societal clans

    oai_token-act-pair · gpt-3.5-turbo

    terms related to familial or group affiliations, specifically clans and dynasties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.80
     Indiana
    -0.75
    Indiana
    -0.72
    neutral
    -0.69
    Portland
    -0.69
     Statue
    -0.68
    buquerque
    -0.68
     Wolfe
    -0.68
     Amtrak
    -0.66
     Verizon
    -0.66
    POSITIVE LOGITS
     clan
    3.11
     clans
    2.64
     Clan
    2.46
     dynasty
    2.28
     dyn
    2.02
     lineage
    1.78
     caste
    1.75
     patriarch
    1.54
     hereditary
    1.46
     familial
    1.34
    Activations Density 0.051%

    No Known Activations